Home

Awesome

NeRF++

Codebase for arXiv preprint "NeRF++: Analyzing and Improving Neural Radiance Fields"

Demo

Data

Create environment

conda env create --file environment.yml
conda activate nerfplusplus

Training (Use all available GPUs by default)

python ddp_train_nerf.py --config configs/tanks_and_temples/tat_training_truck.txt

Note: In the paper, we train NeRF++ on a node with 4 RTX 2080 Ti GPUs, which took ∼24 hours.

Testing (Use all available GPUs by default)

python ddp_test_nerf.py --config configs/tanks_and_temples/tat_training_truck.txt \
                        --render_splits test,camera_path

Note: due to restriction imposed by torch.distributed.gather function, please make sure the number of pixels in each image is divisible by the number of GPUs if you render images parallelly.

Pretrained weights

I recently re-trained NeRF++ on the tanks and temples data for another project. Here are the checkpoints (google drive) just in case you might find them useful.

Citation

Plese cite our work if you use the code.

@article{kaizhang2020,
    author    = {Kai Zhang and Gernot Riegler and Noah Snavely and Vladlen Koltun},
    title     = {NeRF++: Analyzing and Improving Neural Radiance Fields},
    journal   = {arXiv:2010.07492},
    year      = {2020},
}

Generate camera parameters (intrinsics and poses) with COLMAP SfM

You can use the scripts inside colmap_runner to generate camera parameters from images with COLMAP SfM.

Visualize cameras in 3D

Check camera_visualizer/visualize_cameras.py for visualizing cameras in 3D. It creates an interactive viewer for you to inspect whether your cameras have been normalized to be compatible with this codebase. Below is a screenshot of the viewer: green cameras are used for training, blue ones are for testing, while yellow ones denote a novel camera path to be synthesized; red sphere is the unit sphere.

<!-- ![](camera_visualizer/screenshot_lowres.png) --> <img src="camera_visualizer/screenshot_lowres.png" width="280">

Inspect camera parameters

You can use camera_inspector/inspect_epipolar_geometry.py to inspect if the camera paramters are correct and follow the Opencv convention assumed by this codebase. The script creates a viewer for visually inspecting two-view epipolar geometry like below: for key points in the left image, it plots their correspoinding epipolar lines in the right image. If the epipolar geometry does not look correct in this visualization, it's likely that there are some issues with the camera parameters.

<img src="camera_inspector/screenshot_lowres.png" width="600">